Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5430 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.6354. Min Act: -0.0002

Data Index: 387112 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.6108. Min Act: -0.0002

Data Index: 573735 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.6113. Min Act: -0.0003

Data Index: 1040065 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5936. Min Act: -0.0002

Data Index: 1356895 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.6012. Min Act: -0.0002

Data Index: 315643 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5917. Min Act: -0.0002

Data Index: 896976 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5733. Min Act: -0.0002

Data Index: 382924 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5725. Min Act: -0.0002

Data Index: 1205515 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5704. Min Act: -0.0002

Data Index: 81111 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5717. Min Act: -0.0002

Data Index: 273267 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5708. Min Act: -0.0003

Data Index: 1173161 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5586. Min Act: -0.0002

Data Index: 149043 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5472. Min Act: -0.0002

Data Index: 331405 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5481. Min Act: -0.0002

Data Index: 962142 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5432. Min Act: -0.0002

Data Index: 703486 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5326. Min Act: -0.0002

Data Index: 1318920 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5291. Min Act: -0.0002

Data Index: 974402 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5256. Min Act: -0.0002

Data Index: 489483 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5300. Min Act: -0.0002

Data Index: 904113 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.6354. Min Range: -0.6354

Max Act: 0.5271. Min Act: -0.0003

Data Index: 1336383 (C4 (Web Text))

Max Activating Token Index: 143